Search NASA⌕ Search

SEARCH · Search NASA

Results for “Markov decision process”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 records

K-Spin Hamiltonian for Quantum-Resolvable Markov Decision Processes

The Markov decision process is the mathematical formalization underlying the modern field of reinforcement learning when transition and reward functions are unknown. We derive a pseudo-Boolean cost function that is equivalent to a K-spin Hamiltonian representation of the discrete, finite, discounted Markov decision process with infinite horizon. This K-spin Hamiltonian furnishes a starting point from which to solve for an optimal policy using heuristic quantum algorithms such as adiabatic quantum annealing and the quantum approximate optimization algorithm on near-term quantum hardware. In arguing that the variational minimization of our Hamiltonian is approximately equivalent to the Bellman optimality condition for a prevalent class of environments we establish an interesting analogy with classical field theory. Along with proof-of-concept calculations to corroborate our formulation by simulated and quantum annealing against classical Q-Learning, we analyze the scaling of physical resources required to solve our Hamiltonian on quantum hardware.

Hamiltonian↗

Hybrid Discrete-Continuous Markov Decision Processes

This paper proposes a Markov decision process (MDP) model that features both discrete and continuous state variables. We extend previous work by Boyan and Littman on the mono-dimensional time-dependent MDP to multiple dimensions. We present the principle of lazy discretization, and piecewise constant and linear approximations of the model. Having to deal with several continuous dimensions raises several new problems that require new solutions. In the (piecewise) linear case, we use techniques from partially- observable MDPs (POMDPS) to represent value functions as sets of linear functions attached to different partitions of the state space.

Feng, Zhengzhu↗

Mean-Variance Problems for Finite Horizon Semi-Markov Decision Processes

This paper deals with a mean-variance problem for finite horizon semi-Markov decision processes. The state and action spaces are Borel spaces, while the reward function may be unbounded. The goal is to seek an optimal policy with minimal finite horizon reward variance over the set of policies with a given mean. Using the theory of N-step contraction, we give a characterization of policies with a given mean and convert the second order moment of the finite horizon reward to a mean of an infinite horizon reward/cost generated by a discrete-time Markov decision processes (MDP) with a two dimension state space and a new one-step reward/cost under suitable conditions. We then establish the optimality equation and the existence of mean-variance optimal policies by employing the existing results of discrete-time MDPs. We also provide a value iteration and a policy improvement algorithms for computing the value function and mean-variance optimal policies, respectively. In addition, a linear program and the dual program are developed for solving the mean-variance problem.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Conditions for the Solvability of the Linear Programming Formulation for Constrained Discounted Markov Decision Processes

We consider a discrete-time constrained discounted Markov decision process (MDP) with Borel state and action spaces, compact action sets, and lower semi-continuous cost functions. We introduce a set of hypotheses related to a positive weight function which allow us to consider cost functions that might not be bounded below by a constant, and which imply the solvability of the linear programming formulation of the constrained MDP. In particular, we establish the existence of a constrained optimal stationary policy. Our results are illustrated with an application to a fishery management problem.

97 MATHEMATICS AND COMPUTING↗

Markov Decision Process based Trajectory Planning for UAVs under Uncertain Wind Conditions

In this paper we propose a Markov Decision Process (MDP) algorithm for path-planning of Unmanned Aviation Vehicles (UAVs) under varying wind conditions. Solutions to path-planning for UAVs are becoming increasingly necessary as autonomous UAVs continue to enter commercial and government spaces. Path-planning is inherently challenging, as UAVs needs to account for dynamically changing flying conditions such as weather, obstacle or no-fly zones, degraded vehicle health and off-nominal battery power consumption. Machine learning methods such as Markov Decision Process (MDPs) have the potential to revolutionize how vehicles navigate in such uncertain environments. Previous papers have demonstrated the use of MDPs to optimize UAV path-planning for energy consumption under time-varying wind distribution. In this study, UAV trajectories from a pre-determined waypoint to target cell, will be computed on a 7X7 grid environment by optimizing parameters for mission assurance and safety limits in addition to the energy consumption, and operation time. The UAV navigates the grid by taking actions to move in either of the eight cardinal and intercardinal directions, under constant thrust profile. The next state of the UAV is calculated by considering its action, transition probability, obstacle cells and the wind speed magnitude and direction. Both constant and stochastic wind will be considered in this paper, the parameters being extracted from real wind measurements in proximity to an experimental UAV flight. One of the studies to be demonstrated in this paper is that as the unmanned airspace gets more complex with multiple vehicles and environmental uncertainties, trade-offs between energy consumption, operation time, risk tolerance, and mission assurance needs to be made. Further, MDPs are capable of fast computation of UAV trajectories under varying wind, hence making them suitable for in-flight path planners.

decision-making↗

Symbolic Heuristic Search for Factored Markov Decision Processes

We describe a planning algorithm that integrates two approaches to solving Markov decision processes with large state spaces. State abstraction is used to avoid evaluating states individually. Forward search from a start state, guided by an admissible heuristic, is used to avoid evaluating all states. We combine these two approaches in a novel way that exploits symbolic model-checking techniques and demonstrates their usefulness for decision-theoretic planning.

Morris, Robert↗

Distributionally Robust Partially Observable Markov Decision Process with Moment-Based Ambiguity

In this paper, we consider a distributionally robust partially observable Markov decision process (DR-POMDP), where the distribution of the transition-observation probabilities is unknown at the beginning of each decision period, but their realizations can be inferred using side information at the end of each period after an action being taken. We build an ambiguity set of the joint distribution using bounded moments via conic constraints and seek an optimal policy to maximize the worst-case (minimum) reward for any distribution in the set. We show that the value function of DR-POMDP is piecewise linear convex with respect to the belief state and propose a heuristic search value iteration method for obtaining lower and upper bounds of the value function. We conduct numerical studies and demonstrate the computational performance of our approach via testing instances of a dynamic epidemic control problem. Our results show that DR-POMDP can produce more robust policies under misspecified distributions of transition-observation probabilities as compared to POMDP but has less costly solutions than robust POMDP. The DR-POMDP policies are also insensitive to varying parameter in the ambiguity set and to noise added to the true transition-observation probability values obtained at the end of each decision period.

97 MATHEMATICS AND COMPUTING↗

Impulsive Control for Continuous-Time Markov Decision Processes: A Linear Programming Approach

In this paper, we investigate an optimization problem for continuous-time Markov decision processes with both impulsive and continuous controls. We consider the so-called constrained problem where the objective of the controller is to minimize a total expected discounted optimality criterion associated with a cost rate function while keeping other performance criteria of the same form, but associated with different cost rate functions, below some given bounds. Our model allows multiple impulses at the same time moment. The main objective of this work is to study the associated linear program defined on a space of measures including the occupation measures of the controlled process and to provide sufficient conditions to ensure the existence of an optimal control.

97 MATHEMATICS AND COMPUTING↗

Decision-making based on Markov decision process in integrated artificial reasoning framework—Part I: Theory

This paper presents a decision-making framework based on an integrated artificial reasoning framework and Markov decision process (MDP). The integrated artificial reasoning framework provides a physics-based approach that converts system information into state transition models, and the analysis result will be represented by the transition probabilities that can be used with an MDP to find a traceable and explainable optimal pathway. A dynamic Bayesian network (DBN) is well suited for representing the structure of an MDP. The causality information among process variables (or among subsystems) is mathematically represented in a DBN by the conditional probabilities of the node’s states provided different probabilities of the parent node’s states. To define node states in a physically understandable manner, we used multilevel flow modeling (MFM). An MFM follows the fundamental energy and mass conservation laws and supports the selection of process variables that represent the system of interest so that causal relations among process variables are properly captured. An MFM-based DBN supports developing state transition models in an MDP to capture the effect of process variables of system having physical relations. The operators of the target system can capture stochastic system dynamics as multiple subsystem state transitions based on their physical relations and uncertainties coming from component degradation or random failures. We analyzed a simplified exemplary system to illustrate an optimal operational policy using the suggested approach.

Markov decision process↗

Quantum logic gate synthesis as a Markov decision process

Reinforcement learning has witnessed recent applications to a variety of tasks in quantum programming. The underlying assumption is that those tasks could be modeled as Markov decision processes (MDPs). Here, we investigate the feasibility of this assumption by exploring its consequences for single-qubit quantum state preparation and gate compilation. By forming discrete MDPs, we solve for the optimal policy exactly through policy iteration. We find optimal paths that correspond to the shortest possible sequence of gates to prepare a state or compile a gate, up to some target accuracy. Our method works in both the absence and presence of noise and compares favorably to other quantum compilation methods, such as the Ross–Selinger algorithm. This work provides theoretical insight into why reinforcement learning may be successfully used to find optimally short gate sequences in quantum programming.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Transition-Independent Decentralized Markov Decision Processes

There has been substantial progress with formal models for sequential decision making by individual agents using the Markov decision process (MDP). However, similar treatment of multi-agent systems is lacking. A recent complexity result, showing that solving decentralized MDPs is NEXP-hard, provides a partial explanation. To overcome this complexity barrier, we identify a general class of transition-independent decentralized MDPs that is widely applicable. The class consists of independent collaborating agents that are tied up by a global reward function that depends on both of their histories. We present a novel algorithm for solving this class of problems and examine its properties. The result is the first effective technique to solve optimally a class of decentralized MDPs. This lays the foundation for further work in this area on both exact and approximate solutions.

Becker, Raphen↗

Markov Decision Processes for Intelligent, Risk-Informed Asset-Management Decision-Making

Advanced nuclear reactors are a promising option for aiding the world in achieving its net-zero carbon emission goals, however, there are significant challenges to attaining and maintaining economic competitiveness with other sources of electricity. To improve the economic competitiveness of advanced reactor designs, a project was initiated to explore the use of Markov Decision Processes (MDPs) to guide asset-management decision-making during advanced reactor operation. MDPs are a powerful tool for optimizing decision-making in complex environments and their application to advanced reactors can aid in planning maintenance and repair activities to minimize downtime and maximize generation. The described approach expands on previous work regarding the use of MDPs for operational decision-making through the direct incorporation of real-time plant information. The integral MDP analysis includes information from online component diagnostic tools and the plant’s real-time generation risk assessment (GRA) and probabilistic risk assessment (PRA), which evaluate plant risk from both an economic and safety perspective. The result is an asset-management optimization framework that is based on real-time data regarding plant component status and the current best-estimate of plant risk. The paper presents an overview of the theoretical framework to incorporate the different information pathways into an integral MDP analysis, along with example analyses.

Grabaskas, David↗

A Markov Decision Process Framework for Optimal Airport Reconfiguration

The airport runway configuration is defined as a combination set of runways for arrivals and departures used at a point during operation of the airport. An optimal configuration of these runways depends on a number of factors, including traffic demand, wind magnitude and direction, other adverse weather conditions, and noise restrictions, among others. Based on the current state of these factors and predictions of traffic demand and weather conditions, runway configuration changes are made and coordinated between tower controller, other air traffic control facilities, pilots, and ground personnel. Reconfigurations can be quite disruptive to airport operations; minimizing their frequency and scheduling them well in advance is essential for mitigating some of the added workload for controllers and pilots. Unfortunately, deciding on an appropriate time to change is challenging for human decision makers. Not only do multiple factors need to be evaluated, but the uncertainty in their forecasts must also be considered. Previous optimization methods, such as mixed linear integer programming, have been proposed. Although these methods can reason over a large set of variables, they do not systematically handle the uncertainty associated with weather movement, traffic demands, and other variables. In this work, we introduce a Markov Decision Process (MDP)-based decision making framework which can reason effectively over the inherent uncertainties and make optimal decisions on if/when to change the airport configuration. In a prototype implementation, we present a single runway with three aircraft and utilize knowledge of the forecasted wind speed and direction to determine whether to keep or change the current runway configuration. Our aim through this work is to present a framework for airport reconfiguration which can be scalable to additional aircraft, multiple runways, and various input parameters. This technique will optimize the airport reconfiguration procedure by providing a proactive approach, optimizing not just at the next optimal opportunity for a reconfiguration based on varying atmospheric and traffic conditions in the terminal airspace, but also anticipating future necessary reconfigurations. This will eliminate the inefficiencies of frequent changes currently associated with runway reconfiguration procedures.

runway reconfiguration↗

The Discounted Method and Equivalence of Average Criteria for Risk-Sensitive Markov Decision Processes on Borel Spaces

This note concerns discrete-time controlled Markov chains with Borel state and action spaces. Given a nonnegative cost function, the performance of a control policy is measured by the superior limit risk-sensitive average criterion associated with a constant and positive risk sensitivity coefficient. Within such a framework, the discounted approach is used (a) to establish the existence of solutions for the corresponding optimality inequality, and (b) to show that, under mild conditions on the cost function, the optimal value functions corresponding to the superior and inferior limit average criteria coincide on a certain subset of the state space. The approach of the paper relies on standard dynamic programming ideas and on a simple analytical derivation of a Tauberian relation.

97 MATHEMATICS AND COMPUTING↗

Cooperation and Coordination Between Fuzzy Reinforcement Learning Agents in Continuous State Partially Observable Markov Decision Processes

Successful operations of future multi-agent intelligent systems require efficient cooperation schemes between agents sharing learning experiences. We consider a pseudo-realistic world in which one or more opportunities appear and disappear in random locations. Agents use fuzzy reinforcement learning to learn which opportunities are most worthy of pursuing based on their promise rewards, expected lifetimes, path lengths and expected path costs. We show that this world is partially observable because the history of an agent influences the distribution of its future states. We consider a cooperation mechanism in which agents share experience by using and-updating one joint behavior policy. We also implement a coordination mechanism for allocating opportunities to different agents in the same world. Our results demonstrate that K cooperative agents each learning in a separate world over N time steps outperform K independent agents each learning in a separate world over K*N time steps, with this result becoming more pronounced as the degree of partial observability in the environment increases. We also show that cooperation between agents learning in the same world decreases performance with respect to independent agents. Since cooperation reduces diversity between agents, we conclude that diversity is a key parameter in the trade off between maximizing utility from cooperation when diversity is low and maximizing utility from competitive coordination when diversity is high.

Berenji, Hamid R.↗